Essays about: "korsvalidering"

Showing result 1 - 5 of 48 essays containing the word korsvalidering.

  1. 1. Pre-planning of Individualized Ankle Implants Based on Computed Tomography - Automated Segmentation and Optimization of Acquisition Parameters

    University essay from KTH/Fysik

    Author : Matilda Engström Messén; Elvira Moser; [2021]
    Keywords : osteochondral lesions of the talus; computed tomography; U-net; convolutional neural network; dice coefficient; fotled; ledbrosk; osteochondral lesion of the talus; datortomografi; U-net; convolutional neuralt nätverk; dicekoefficient;

    Abstract : The structure of the ankle joint complex creates an ideal balance between mobility and stability, which enables gait. If a lesion emerges in the ankle joint complex, the anatomical structure is altered, which may disturb mobility and stability and cause intense pain. READ MORE

  2. 2. Housing Price Prediction over Countrywide Data : A comparison of XGBoost and Random Forest regressor models

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Erik Henriksson; Kristopher Werlinder; [2021]
    Keywords : Random Forest; XGBoost; predicting housing prices; feature engineering; ensemble learning; boosting; data cleansing; 5foldcrossvalidation.;

    Abstract : The aim of this research project is to investigate how an XGBoost regressor compares to a Random Forest regressor in terms of predictive performance of housing prices with the help of two data sets. The comparison considers training time, inference time and the three evaluation metrics R2, RMSE and MAPE. READ MORE

  3. 3. Evaluation of transferability of Convolutional Neural Network pre-training with regard to image characteristics

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Fanny Ekblad Voltaire; Noah Mannberg; [2021]
    Keywords : ;

    Abstract : This study evaluates the impact of pre-training on a medical classification task and investigates what characteristics if images affect the transferability of learned features from the pre-training. Cardiotocography (CTG) is a combined electronic measurement of the fetal heart rate (FHR) and maternal uterine contractions during labor and delivery and is commonly analyzed to prevent hypoxia. READ MORE

  4. 4. Transformer decoder as a method to predict diagnostic trouble codes in heavy commercial vehicles

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Haris Poljo; [2021]
    Keywords : Diagnostic Trouble Codes; Deep Learning; Machine Learning; Neural Networks; Transformer Decoder; Felkoder; Djupinlärning; Maskininlärning; Neurala Nätverk; Transformer Decoder;

    Abstract : Diagnostic trouble codes (DTC) have traditionally been used by mechanics to figure out what is wrong with a vehicle. A vehicle generates a DTC when a specific condition in the vehicle is met. This condition has been defined by an engineer and represents some fault that has happened. READ MORE

  5. 5. A Comparative study of data splitting algorithms for machine learning model selection

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Delwende Eliane Birba; [2020]
    Keywords : K-fold; cross-validation; Kennard-Stone algorithm; data splitting; bootstrap; overfitting; SPXY; k-faldig korsvalidering; korsvalidering; Kennard-Stone-algoritm; datapartitionering; bootstrap; överanpassning; SPXY;

    Abstract : Data splitting is commonly used in machine learning to split data into a train, test, or validation set. This approach allows us to find the model hyper-parameter and also estimate the generalization performance. In this research, we conducted a comparative analysis of different data partitioning algorithms on both real and simulated data. READ MORE